Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases expressing praise and acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fun
    -0.17
    fun
    -0.16
     Fun
    -0.15
    redo
    -0.15
    enes
    -0.14
    _typeof
    -0.14
    inja
    -0.14
    umont
    -0.14
    /Branch
    -0.14
    chk
    -0.14
    POSITIVE LOGITS
     effort
    0.19
     efforts
    0.18
    ysz
    0.15
     feat
    0.15
    iaz
    0.15
    енÑĮ
    0.14
    ãģ§ãģį
    0.14
    ableObject
    0.14
    icle
    0.14
    ANGLE
    0.14
    Act Density 0.107%

    No Known Activations